© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 30972
    Prev
    Next
    INDEX
    Explanations

    instances of the article "a" or variations of it in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/2-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    478
    +0.19
    1.1%
    156
    +0.18
    1.0%
    137
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    436
    +0.19
    0.07
    377
    +0.18
    0.07
    137
    +0.13
    0.08
    Negative Logits
    lords
    -1.96
    als
    -1.87
    aires
    -1.80
    à±į
    -1.71
    cies
    -1.66
    ups
    -1.62
    rooms
    -1.62
    arily
    -1.61
    aria
    -1.59
    rays
    -1.58
    POSITIVE LOGITS
    Ŀ
    3.20
    ĻĤ
    3.16
    ĸ´
    3.14
    ĵ
    3.00
    Ĵ
    2.99
    ĸ
    2.96
    £
    2.94
    ¼
    2.92
    į
    2.92
    ĥ
    2.91
    Activations Density 0.567%

    No Known Activations